© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99404
    Prev
    Next
    INDEX
    Explanations

    identification tag bolted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     колеса
    -1.06
    咧
    -0.98
     RoutedEventArgs
    -0.98
     sayfası
    -0.98
    gamepad
    -0.94
     rappresenta
    -0.93
    kega
    -0.93
     kaplama
    -0.93
    ₁,
    -0.92
     kağıdı
    -0.92
    POSITIVE LOGITS
     underneath
    1.11
     looks
    1.09
     located
    1.02
     behind
    1.02
    雰囲気
    0.99
     zugänglich
    0.98
     circled
    0.97
     there
    0.94
     nestled
    0.93
     bolted
    0.93
    Activations Density 0.023%

    No Known Activations